Zobrazeno 1 - 10
of 763
pro vyhledávání: '"Brusilovsky, P."'
The generative large language models (LLMs) are increasingly being used for data augmentation tasks, where text samples are LLM-paraphrased and then used for classifier fine-tuning. However, a research that would confirm a clear cost-benefit advantag
Externí odkaz:
http://arxiv.org/abs/2408.16502
Autor:
Hassany, Mohammad, Brusilovsky, Peter, Ke, Jiaze, Akhuseyinoglu, Kamil, Narayanan, Arun Balajiee Lekshmi
Worked examples (solutions to typical programming problems presented as a source code in a certain language and are used to explain the topics from a programming class) are among the most popular types of learning content in programming classes. Most
Externí odkaz:
http://arxiv.org/abs/2402.16235
Autor:
Cegin, Jan, Pecher, Branislav, Simko, Jakub, Srba, Ivan, Bielikova, Maria, Brusilovsky, Peter
The latest generative large language models (LLMs) have found their application in data augmentation tasks, where small numbers of text samples are LLM-paraphrased and then used to fine-tune downstream models. However, more research is needed to asse
Externí odkaz:
http://arxiv.org/abs/2401.06643
Autor:
Lekshmi-Narayanan, Arun-Balajiee, Oli, Priti, Chapagain, Jeevan, Hassany, Mohammad, Banjade, Rabin, Brusilovsky, Peter, Rus, Vasile
Worked examples, which present an explained code for solving typical programming problems are among the most popular types of learning content in programming classes. Most approaches and tools for presenting these examples to students are based on li
Externí odkaz:
http://arxiv.org/abs/2403.05538
Autor:
Hassany, Mohammad, Brusilovsky, Peter, Ke, Jiaze, Akhuseyinoglu, Kamil, Narayanan, Arun Balajiee Lekshmi
Worked examples (solutions to typical programming problems presented as a source code in a certain language and are used to explain the topics from a programming class) are among the most popular types of learning content in programming classes. Most
Externí odkaz:
http://arxiv.org/abs/2312.02105
The emergence of generative large language models (LLMs) raises the question: what will be its impact on crowdsourcing? Traditionally, crowdsourcing has been used for acquiring solutions to a wide variety of human-intelligence tasks, including ones i
Externí odkaz:
http://arxiv.org/abs/2305.12947
Knowledge Tracing (KT), which aims to model student knowledge level and predict their performance, is one of the most important applications of user modeling. Modern KT approaches model and maintain an up-to-date state of student knowledge over a set
Externí odkaz:
http://arxiv.org/abs/2210.09013
Carousel-based recommendation interfaces allow users to explore recommended items in a structured, efficient, and visually-appealing way. This made them a de-facto standard approach to recommending items to end users in many real-life recommenders. I
Externí odkaz:
http://arxiv.org/abs/2209.13426
Autor:
Brusilovsky, Idan, Tsarfaty, Reut
Tokenizing raw texts into word units is an essential pre-processing step for critical tasks in the NLP pipeline such as tagging, parsing, named entity recognition, and more. For most languages, this tokenization step straightforward. However, for lan
Externí odkaz:
http://arxiv.org/abs/2203.10845
Recent advances in deep learning have transformed many fields by introducing generic embedding spaces, capable of achieving great predictive performance with minimal labeling effort. The geology field has not yet met such success. In this work, we in
Externí odkaz:
http://arxiv.org/abs/2108.08870